© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10026
    Prev
    Next
    INDEX
    Explanations

    instances of the word "you" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "You" and implies disagreement or counter-argument

    np_acts-logits-general · gemini-2.0-flash

    you followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.65
    NewUrlParser
    -0.64
    tvguidetime
    -0.61
    usercontent
    -0.57
    routeProvider
    -0.55
    syms
    -0.54
    AddTagHelper
    -0.54
     OnInit
    -0.53
    原始内容存档于
    -0.53
     NgModule
    -0.52
    POSITIVE LOGITS
     mentioned
    0.86
     clearly
    0.81
     obviously
    0.75
     seem
    0.73
     misunderstand
    0.73
     seemed
    0.72
     mention
    0.71
     misunderstood
    0.69
     verkar
    0.69
    Clearly
    0.68
    Activations Density 0.213%

    No Known Activations